INDEX

Explanations

Judge

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 harmony

-0.07

 Soul

-0.07

 valores

-0.07

 lifestyles

-0.07

oms

-0.07

Market

-0.07

ei

-0.07

 services

-0.07

 bags

-0.07

 Wein

-0.07

POSITIVE LOGITS

 judge

0.12

Judge

0.11

 judges

0.10

 Judge

0.10

 judging

0.09

 Predicate

0.09

UDGE

0.08

 бать

0.08

 Rodriguez

0.07

 Judges

0.07

Activations Density 0.009%

Judge

No Comments

No Known Activations